mm: postpone page table allocation until we have page to map

The idea (and most of code) is borrowed again: from Hugh's patchset on
huge tmpfs[1].

Instead of allocation pte page table upfront, we postpone this until we
have page to map in hands.  This approach opens possibility to map the
page as huge if filesystem supports this.

Comparing to Hugh's patch I've pushed page table allocation a bit
further: into do_set_pte().  This way we can postpone allocation even in
faultaround case without moving do_fault_around() after __do_fault().

do_set_pte() got renamed to alloc_set_pte() as it can allocate page
table if required.

[1] http://lkml.kernel.org/r/[email protected]

Link: http://lkml.kernel.org/r/1466021202-61880-10-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: kiryl

include/linux/mm.h

@@ -330,6 +330,13 @@ struct fault_env {
 					 * Protects pte page table if 'pte'
 					 * is not NULL, otherwise pmd.
 					 */
+	pgtable_t prealloc_pte;		/* Pre-allocated pte page table.
+					 * vm_ops->map_pages() calls
+					 * alloc_set_pte() from atomic context.
+					 * do_fault_around() pre-allocates
+					 * page table to avoid allocation from
+					 * atomic context.
+					 */
 };
 
 /*
@@ -618,7 +625,8 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-void do_set_pte(struct fault_env *fe, struct page *page);
+int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
+		struct page *page);
 #endif
 
 /*

mm/filemap.c

@@ -2144,11 +2144,6 @@ void filemap_map_pages(struct fault_env *fe,
 			start_pgoff) {
 		if (iter.index > end_pgoff)
 			break;
-		fe->pte += iter.index - last_pgoff;
-		fe->address += (iter.index - last_pgoff) << PAGE_SHIFT;
-		last_pgoff = iter.index;
-		if (!pte_none(*fe->pte))
-			goto next;
 repeat:
 		page = radix_tree_deref_slot(slot);
 		if (unlikely(!page))
@@ -2186,14 +2181,23 @@ void filemap_map_pages(struct fault_env *fe,
 
 		if (file->f_ra.mmap_miss > 0)
 			file->f_ra.mmap_miss--;
-		do_set_pte(fe, page);
+
+		fe->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+		if (fe->pte)
+			fe->pte += iter.index - last_pgoff;
+		last_pgoff = iter.index;
+		if (alloc_set_pte(fe, NULL, page))
+			goto unlock;
 		unlock_page(page);
 		goto next;
 unlock:
 		unlock_page(page);
 skip:
 		put_page(page);
 next:
+		/* Huge page is mapped? No need to proceed. */
+		if (pmd_trans_huge(*fe->pmd))
+			break;
 		if (iter.index == end_pgoff)
 			break;
 	}